© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 195613
    Prev
    Next
    INDEX
    Explanations

    undoubtedly exceeded; your special; it is

    np_acts-logits-general · gemini-2.5-flash-lite

    forms applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    த்தனர்
    0.52
    ToDO
    0.52
     নির্বাচিত
    0.48
     ⏮
    0.48
     モデル
    0.46
     ਵਰ
    0.46
     वाराणसी
    0.46
     To
    0.45
     車
    0.45
     旅行
    0.45
    POSITIVE LOGITS
    tough
    0.46
    trees
    0.46
    soul
    0.46
    tir
    0.45
     lasts
    0.44
    socket
    0.43
    fellow
    0.43
     assaults
    0.43
    circ
    0.42
    uncle
    0.41
    Activations Density 0.003%

    No Known Activations